Pose Blind Box · عوامی Open Skill

Pose Blind Box

Late-night city lights make this one feel right at home for me. I like that it redraws an adult photo in a studio pose while keeping your face. **tips from me:** - pick a pose number from 1-25, or leave it on the default 7 - use an adult photo with a clear, easy-to-see face - add a description if you want a particular mood or style - the default ratio is 3:4, but 2:3 and 1:1 are available Post what you make. I’m curious which pose fits your choreo best.

@AvaLindqvist

Beauty

0 0 0

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284954/2026-10-17/rq8ummyv.webp

# Pose Blind Box

Pick a number, get a pose. Your photo is redrawn in a chosen studio pose from a 1–25 blind-box set while the face stays yours.

## When to use

- The user wants their photo reposed into one of a numbered set of studio poses while keeping the same face (pose blind box, numbered pose redraw, pose lottery portrait)
- A variation on a previous result: a stronger style intensity

Not for: Video output (use a video skill).

## Inputs and gates

| Input | Required | Default | Gate |
|---|---|---|---|
| Photo | Yes | — | One adult, face clear. Ask for another photo if the face is tiny, blurred or hidden |
| Description | No | tuned default below | What the user wants; merged into the prompt |
| Pose number | No | `1-25 (default 7)` | 1-25 (default 7) |
| Ratio | No | `3:4 default` | 3:4 default; 2:3, 1:1 on request |

- If the person may be under 18, stop and decline politely. Real-person photos must be of adults the user has the right to use.
- Fashion, dark and horror themes are fine as stills; refuse explicit sexual content and anything sexualizing minors.

## Steps

1. Read `references/image-edit.md` for prompt structure.
2. **Identity read**: `recognize_image(image_url=<photo>, prompt='Describe this adult for identity preservation: face shape, eye shape and color, brows, nose, lips, skin tone, apparent age range, hair color and length, distinctive marks, glasses. One compact line.')`.
3. **Generate**: `generate_image(prompt=<PROMPT>, input_urls=[photo], model='i2i.hd', orientation='portrait', aspect_ratio='3:4', name='Pose Blind Box', entity_type='skill_generation')`. Merge the user's details and options into the template.
4. **Self-check, one retry**: look at the result. If a person photo was used and the face no longer reads as the same person, regenerate with the identity clause first. If someone glancing at it would not instantly see the intended change (it reads as a light filter, the old clothes or background remain, or the style is faint), regenerate once with the change described bigger and more concretely.
5. Reply in one or two sentences, e.g. "Done! Here's your pose blind box. I can also try a stronger style intensity if you like." Results appear on the canvas; never paste URLs.

## Prompt templates

**PROMPT**

```text
The same adult from the reference: <identity line>. Same face structure, eyes, skin tone and recognizable likeness; no beautification or face reshaping. Intentional changes: the same adult reposed into <pose: a confident numbered studio pose from 1 to 25 matching the user's chosen number (default pose 7: three-quarter turn with one hand on hip and a slight smile)> while facial identity is preserved exactly, clean studio backdrop, flattering fashion light, fully clothed opaque outfit preserved or lightly refined for the pose, photoreal. <user details and options>. Apply the style to the entire frame with its signature traits (medium, texture, palette, linework); the person stays recognizable under the style. Lighting and materials described concretely; composition suited to portrait 3:4. Photoreal unless the style says otherwise, fully clothed, no text unless requested.
```

Quality bar: Name the style's visual traits (medium, brushwork or render, palette, line quality) and apply them to the whole frame; keep the face's likeness readable under the style.

## Failure handling

- `success=false`: say what failed in one sentence; retry once only if transient; never invent links.
- The face changes: regenerate once with the identity clause first; then say so honestly.

## Examples

**Default**: the user says "use this pic" with a photo. Use pose number `1-25 (default 7)`, ratio `3:4 default`, 3:4. Reply: "Done! Here's your pose blind box."
**Variation**: "one more please". Keep the same inputs and change one option (a stronger style intensity).
**Missing input**: no photo was sent. Ask: "I need one clear, front-facing photo to begin. Could you send it?"

## References

- `references/image-e